© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 71296
    Prev
    Next
    INDEX
    Explanations

    line endings and syntax punctuation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ottes
    -0.06
     PIC
    -0.05
     instead
    -0.05
    617
    -0.05
     Protest
    -0.05
    /git
    -0.05
     inde
    -0.05
    ÑĤеÑĢн
    -0.05
    ĵåIJį
    -0.05
     Vs
    -0.05
    POSITIVE LOGITS
     respectively
    0.09
    icÃŃ
    0.08
    обов
    0.08
    ãģ£ãģ¡
    0.07
    icana
    0.07
    IVAL
    0.07
    nerRadius
    0.07
     dolu
    0.07
    æī¬
    0.07
    Ŀ¼
    0.07
    Activations Density 0.045%

    No Known Activations